Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    foreign languages and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sales
    0.49
    Prosecutors
    0.46
     Prosecutor
    0.46
     господар
    0.45
     Website
    0.44
     bask
    0.44
    覓
    0.44
    طة
    0.44
    鸪
    0.43
    ᄈ
    0.43
    POSITIVE LOGITS
    Gö
    0.50
     popula
    0.48
    ங்களும்
    0.48
    in
    0.47
    かかる
    0.47
    supseteq
    0.47
    UL
    0.46
    ங்களையும்
    0.46
     piti
    0.46
    dub
    0.46
    Act Density 0.000%

    No Known Activations